Entity Embedding Analogy for Implicit Link Discovery

Nada Mimouni 1 Jean-Claude Moissinac 2 Anh Vu
1 RCLN
LIPN - Laboratoire d'Informatique de Paris-Nord
Abstract : In this work we are interested in the problem of knowledge graphs (KG) incompleteness that we propose to solve by discovering implicit triples using observed ones in the incomplete graph leveraging analogy structures deducted from KG embedding model. We use a language modelling approach that we adapt to entities and relations. The first results show that analogical inferences in the projected vector space is relevant for link prediction task.
Document type :
Conference papers
Complete list of metadatas

Cited literature [10 references]  Display  Hide  Download

https://hal.telecom-paristech.fr/hal-02281145
Contributor : Jean-Claude Moissinac <>
Submitted on : Monday, September 9, 2019 - 4:27:34 PM
Last modification on : Thursday, September 12, 2019 - 1:14:14 AM

File

ESWC_Poster.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02281145, version 1

Collections

Citation

Nada Mimouni, Jean-Claude Moissinac, Anh Vu. Entity Embedding Analogy for Implicit Link Discovery. ESWC 2019, Jun 2019, Portoroz, Slovenia. ⟨hal-02281145⟩

Share

Metrics

Record views

14

Files downloads

29